wayfinder
Warn
Audited by Snyk on Jul 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). SKILL.md:117-123 describes the runtime workflow where the user provides a map (URL/number) and the agent “loads the map” and then “d[raws] … full content of the ticket” from the issue tracker, which is outsider-authored free text (issue/ticket bodies written by other people) that the agent reads into its LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata